{"id":"W6969222856","doi":"10.5683/sp3/5wpwjt","title":"Analyse de jeux de données, présélection et détermination de modèles | Dataset analysis, model shortlisting, and model determination","year":2025,"lang":"fr","type":"dataset","venue":"Borealis","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Field (mathematics); Set (abstract data type); Context (archaeology); Feature (linguistics); Matching (statistics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008654118,0.003342281,0.001879585,0.006376253,0.001275892,0.005389649,0.003872318,0.002017637,0.01975642],"category_scores_gemma":[0.04421162,0.001370408,0.004801413,0.005166611,0.0009375468,0.003947802,0.003282741,0.003861389,0.0195895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002780229,"about_ca_system_score_gemma":0.00449085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02387047,"about_ca_topic_score_gemma":0.04536981,"domain_scores_codex":[0.9930226,0.001561666,0.001180387,0.001792613,0.002094619,0.0003482623],"domain_scores_gemma":[0.9845547,0.008222199,0.0005628968,0.004440677,0.001888457,0.0003310848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002878598,0.000129856,0.004818121,0.0031987,0.0004087484,0.0001673201,0.0001969835,0.006570912,0.001631068,0.006819514,0.9033498,0.07242119],"study_design_scores_gemma":[0.0003683916,0.0001545069,0.01156686,0.0009759185,0.0002291922,0.0006224661,0.0003193885,0.04196022,0.006827576,0.02450992,0.9122856,0.0001799122],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.004731846,0.001596714,0.04061302,0.001166178,0.0004093691,0.0004009834,0.9045744,0.04172003,0.004787352],"genre_scores_gemma":[0.004783001,0.0003857675,0.03426349,0.0002129797,0.00003214096,0.0005648706,0.9568398,0.001577552,0.001340297],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02387047,"threshold_uncertainty_score":0.06609178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04066982149311352,"score_gpt":0.3461302508539552,"score_spread":0.3054604293608417,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}